Recurrent Neural Networks Are Universal Approximators With Stochastic Inputs

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

Neural networks have shown to be a powerful tool to represent the ground state of quantum many-body systems, including fermionic systems. However, efficiently integrating lattice symmetries into neural representations remains a significant challenge. In th ...

Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organized in a hierarchical and combinatorial manner, which neural networks capture d ...

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

A search is presented for the pair production of new heavy resonances, each decaying into a top quark (t) or antiquark and a gluon (g). The analysis uses data recorded with the CMS detector from proton-proton collisions at a center-of-mass energy of 13 TeV ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Unmanned vehicles have become indispensable tools in various fields such as agriculture, environmental monitoring, and disaster response. A crucial component of these platforms is sensor fusion. As measurements are inherently noisy, certain variables canno ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

Real-time condition monitoring is crucial for the reliable and efficient operation of complex systems. However, relying solely on physical sensors can be limited due to their cost, placement constraints, or inability to directly measure certain critical pa ...

The process of protein aggregation, central to neurodegenerative diseases like Huntington’s, is challenging to study due to its unpredictable nature and relatively rapid kinetics. Understanding its biomechanics is crucial for unraveling its role in disease ...

Recurrent Neural Networks Are Universal Approximators With Stochastic Inputs

Chattez avec Graph Search

Learning to Reason with Neural Networks: Principles and Methods

Computational design of complex protein folds and soluble analogs of membrane proteins

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

A comparative analysis of gene expression profiling by statistical and machine learning approaches

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

Sequential Reasoning with Socially Caused Beliefs

Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations

A phase transition in diffusion models reveals the hierarchical nature of data

Person Re-Identification and its Application to Multi-Object Tracking

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Search for Pair Production of Heavy Particles Decaying to a Top Quark and a Gluon in the Lepton Plus Jets Final State in Proton-proton Collisions at √s=13 Tev

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Factor-graph Optimisation with Vehicle Dynamic Models for Mapping & Sensing Applications

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Graph neural networks for virtual sensing in complex systems: Addressing heterogeneous temporal dynamics

Self-driving microscopy detects the onset of protein aggregation and enables intelligent Brillouin imaging